AI-First Scraper MCP Server

Adds three tools to any MCP-compatible agent: No more "the model called curl and then tried to parse 80kB of ad HTML.". It runs locally over stdio via the published package.

People connecting web scraping tools to Claude, Cursor, VS Code, or another MCP client. The project is written in Python.

VERIFIED ACTIVE

LAST COMMIT 2026-05-19 · ★ 2 · #59 OF 78 MAINTAINED WEB SCRAPING · VERIFIED 2026-08-25

MIT · Python servers · how we verify → /methodology

01 · Install AI-First Scraper

before you install - you'll need

Set SCRAPER_URL, SEARCH_URL, AFS_TIMEOUT before connecting.

Claude Code

claude mcp add yubinkim444-ai-first-scraper-mcp -- uvx ai-first-scraper-mcp

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "yubinkim444-ai-first-scraper-mcp": {
      "command": "uvx",
      "args": [
        "ai-first-scraper-mcp"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license MIT - declared in the repository

pypi package ai-first-scraper-mcp - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.yubinkim444 is GitHub-verified and matches the repo owner

03 · Who maintains AI-First Scraper

AI-First Scraper is maintained by yubinkim444. We track 2 MCP servers from yubinkim444 - 2 actively maintained, 3 combined GitHub stars, oldest repo from May 2026.

04 · Facts

repository: github.com/yubinkim444/ai-first-scraper-mcp
category: web scraping - ranked #59 of 78 actively-maintained web scraping servers as of 2026-08-25.
registry: io.github.yubinkim444/ai-first-scraper-mcp (active, first published 2026-05-19)
packages: pypi:ai-first-scraper-mcp

05 · AI-First Scraper FAQ

What is AI-First Scraper?

Adds three tools to any MCP-compatible agent: No more "the model called curl and then tried to parse 80kB of ad HTML.". It runs locally over stdio via the published package.

Is AI-First Scraper still maintained?

Yes - as of 2026-08-25, its last commit was 2026-05-19. We re-verify nightly.

How do I install AI-First Scraper?

Run `uvx ai-first-scraper-mcp`. The README documents 3 environment variables (SCRAPER_URL, SEARCH_URL, AFS_TIMEOUT) to set first. Set SCRAPER_URL, SEARCH_URL, AFS_TIMEOUT before connecting. You can also paste the ready-made client config above.

Does AI-First Scraper run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

06 · Alternatives to AI-First Scraper

Alternatives to AI-First Scraper

Maintained web scraping servers if AI-First Scraper isn't the fit.

Pairs well with

Servers that cover what AI-First Scraper doesn't - only shown when the pairing reason fits the companion.

More web scraping MCP servers · Zenrows MCP · Web Researcher MCP · Librecrawl - Technical SEO Audit MCP Server · Google News & Trends MCP · Web Reaper

More Python MCP servers · DB Connect MCP · ITASCA MCP Server · YADE MCP Server · Multisim MCP · Ugs MCP · see all